A Deep-Learning Approach toward Rational Molecular Docking Protocol Selection.
- Jiménez-Luna J Department of Chemistry and Applied Biosciences, RETHINK, ETH Zuerich, Vladimir-Prelog-Weg 4, 8093 Zuerich, Switzerland.
- Cuzzolin A Molecular Modeling Section, Department of Pharmaceutical and Pharmacological Sciences, University of Padova, 35131 Padova, Italy.
- Bolcato G Molecular Modeling Section, Department of Pharmaceutical and Pharmacological Sciences, University of Padova, 35131 Padova, Italy.
- Sturlese M Molecular Modeling Section, Department of Pharmaceutical and Pharmacological Sciences, University of Padova, 35131 Padova, Italy.
- Moro S Molecular Modeling Section, Department of Pharmaceutical and Pharmacological Sciences, University of Padova, 35131 Padova, Italy.
- 2020-05-31
Published in:
- Molecules (Basel, Switzerland). - 2020
English
While a plethora of different protein-ligand docking protocols have been developed over the past twenty years, their performances greatly depend on the provided input protein-ligand pair. In this study, we developed a machine-learning model that uses a combination of convolutional and fully connected neural networks for the task of predicting the performance of several popular docking protocols given a protein structure and a small compound. We also rigorously evaluated the performance of our model using a widely available database of protein-ligand complexes and different types of data splits. We further open-source all code related to this study so that potential users can make informed selections on which protocol is best suited for their particular protein-ligand pair.
- Language
-
- English
- Open access status
- gold
- Identifiers
-
- DOI 10.3390/molecules25112487
- PMID 32471211
- Persistent URL
- https://folia.unifr.ch/global/documents/199913
Statistics
Document views: 9
File downloads:
- fulltext.pdf: 0